Add MistralAI LLM client

[indegro]

Motivation and Context

MistralAI provides a list of models for working with completions, agents. Also the company has a high-speed inference.
Another aspect -- GDPR, models are deployed in Europe and it allows working with projects where GDPR is crucial.

Original issue -- #530

Breaking Changes

---

Type of the changes

• New feature (non-breaking change which adds functionality)
• Bug fix (non-breaking change which fixes an issue)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update
• Tests improvement
• Refactoring

Checklist

• The pull request has a description of the proposed change
• I read the Contributing Guidelines before opening the pull request
• The pull request uses develop as the base branch
• Tests for the changes have been added
• All new and existing tests passed

Additional steps for pull requests adding a new feature

• An issue describing the proposed change exists
• The pull request includes a link to the issue
• The change was discussed and approved in the issue
• Docs have been added / updated

[Ololoshechkin]

Thank you so much for your contribution! Appreciate that a lot!

Please consider adding KDocs for public API, and supporting media types.
Adding all models is rather optional (we can auto-generate it later) but nice to have :)

[devcrocod]

Thank you for your contribution!

I have reviewed the client class and left a few comments. please take a look at them

From what I can tell, Mistral is generally similar to an OpenAI-like client. To address this, you might consider:

• Inheriting from AbstractOpenAILLMClient. This way, you would not need to reimplement the core logic and types
• Waiting for this PR #645 to be merged, and then adding only the Mistral request.
  Compared to OpenAI, Mistral is missing many fields and instead introduces a different field, prompt_mode

[antoniibelyshev]

Thank you for your contribution!

Could you please also implement the executeMultipleChoices method to support the multiple choices functionality supported by the parameter n?

[Copilot]

Pull Request Overview

This PR adds comprehensive MistralAI LLM client integration to the Koog framework, enabling support for MistralAI's chat, embedding, and moderation models with full parameter control and multimodal capabilities.

• Adds new MistralAI client implementation with support for chat completions, embeddings, and content moderation
• Integrates MistralAI provider across all framework modules including Spring Boot starter and Ktor integration
• Includes comprehensive test coverage for serialization, parameters, models, and client functionality

Reviewed Changes

Copilot reviewed 39 out of 40 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
settings.gradle.kts	Adds MistralAI client module to build configuration
prompt/prompt-model/src/commonMain/kotlin/ai/koog/prompt/dsl/ModerationAPI.kt	Adds hashCode method to ModerationCategory
prompt/prompt-llm/src/commonMain/kotlin/ai/koog/prompt/llm/LLMProvider.kt	Adds MistralAI provider definition
prompt-executor-mistralai-client/	Core MistralAI client implementation with models, parameters, and API integration
prompt-executor-llms-all/	Adds simple MistralAI executor factory method
Spring Boot starter modules	Adds auto-configuration and properties for MistralAI integration
Ktor modules	Adds configuration loading and model parsing for MistralAI
Examples	Adds MistralAI usage examples and tool integration

Comments suppressed due to low confidence (2)

prompt/prompt-executor/prompt-executor-clients/prompt-executor-mistralai-client/src/commonMain/kotlin/ai/koog/prompt/executor/clients/mistralai/models/MistralAIChatCompletion.kt:1

• The moderationPath property is declared as val instead of var, making it immutable and always null. This prevents customization of the moderation API path.

package ai.koog.prompt.executor.clients.mistralai.models

koog-ktor/src/commonMain/kotlin/ai/koog/ktor/KoogAgentsConfig.kt:1

• Comment incorrectly refers to 'Google configuration' in the MistralAI configuration section.

package ai.koog.ktor

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[devcrocod]

So the PR doesn’t get blocked

[antoniibelyshev]

Thank you, looks good

[devcrocod]

@Ololoshechkin please take a look at this PR